Skip to content

Build a deep learning model for predicting the price of wine given the description

License

Notifications You must be signed in to change notification settings

floydhub/regression-template

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Regression using a Wide & Deep model

Predicting the price of an object given the historical data is one of the most common task of ML, usually achieved with the Linear Regression model. In this project the Linear Layer will be only the top of the iceberg of a model which combines the wideness of ML model and the deepness of DL model for NLP. The goal is to predict the price of a wine from its description (and variety).

Try it now

Run on FloydHub

Click this button to open a Workspace on FloydHub that will train this model.

Predicting price of wine

In this notebook, we will build a classifier to correctly predict the price of a wine from its description. More in detail, we will combine the strength of ML and DL learning using a Wide & Deep Model, which provides really good performance for Regression and Recommendation tasks.

regression

We will use the Kaggle's Wine Reviews dataset for training our model. The dataset contains 10 columns and 150k rows of wine reviews.

We will:

  • Preprocess text data for NLP
  • Build and train a Wide & Deep model using Keras and Tensorflow
  • Evaluate our model on the test set
  • Run the model on your own movie reviews!